bloomz.cpp
C++ implementation for BLOOM (by NouamaneTazi)
ggml
Tensor library for machine learning (by the-crypt-keeper)
bloomz.cpp | ggml | |
---|---|---|
4 | 3 | |
806 | 1 | |
- | - | |
6.0 | 10.0 | |
about 1 year ago | 11 months ago | |
C | C | |
MIT License | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
bloomz.cpp
Posts with mentions or reviews of bloomz.cpp.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-07-06.
-
My largest ever quants, GPT 3 sized! BLOOMZ 176B and BLOOMChat 1.0 176B
Possibly. There's a llama.cpp fork called bloomz.cpp but it's not been updated in 2 months. So it's not going to support any of the fancy new quantisation methods, performance improvements, GPU acceleration, etc.
- Bloomz.cpp: C++ implementation for BLOOM models
- Bloomz.cpp: Run multilingual BLOOM model with C++
-
[N] bloomz.cpp: Run any BLOOM-like model in pure C++
bloomz.cpp allows running inference of BLOOM-like models in pure C/C++ (inspired by llama.cpp). It supports all models that can be loaded with BloomForCausalLM.from_pretrained(). For example, you can achieve 16 tokens per second on a M1 Pro.
ggml
Posts with mentions or reviews of ggml.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-07-06.
-
My largest ever quants, GPT 3 sized! BLOOMZ 176B and BLOOMChat 1.0 176B
You need my ggml fork until #343 is merged into ggml to use it.
-
Why is nobody talking about this? New best Apache licensed code bot on hugging face or just hype?
Note: GGML headrev is broken something after my PR did bad things, use my fork for now - https://github.com/the-crypt-keeper/ggml/tree/opencoder_eot
-
GGML for Falcon7B, SantaCoder 1B, TinyStarCoder 160M
GGML fork: https://github.com/the-crypt-keeper/ggml/tree/starcoder_repeat_penalty (use examples/starcoder)
What are some alternatives?
When comparing bloomz.cpp and ggml you can also consider the following projects:
libvips - A fast image processing library with low memory needs.
openchat - OpenChat: Advancing Open-source Language Models with Imperfect Data
llama.cpp - LLM inference in C/C++
ggml - Tensor library for machine learning
lm-evaluation-harness - A framework for few-shot evaluation of language models.
can-ai-code - Self-evaluating interview for AI coders
vosk - VOSK Speech Recognition Toolkit
ggml - Falcon7B + Falcon40B support - in branch falcon40b. Now all good and working. But main action now in https://github.com/cmp-nct/ggllm.cpp